A TEXT-INDEPENDENT SPEAKER RECOGNITION SYSTEM BASED ON VOWEL SPOTTING

An automatic text-independent speaker recognition system suitable for identification and verification purposes is presented. The system is b ased on spotting the vowels of the test utterance, extracting paramete r vectors and classifying them into a speaker-dependent reference data base. This database consists of L prototypes for every speaker, repres enting the vowels of the language, which are estimated from L vowel cl usters. These are formed by applying a modified k-means algorithm on t he patterns extracted from the vowels of training utterances. The patt erns of the training utterances are stored in a training database to b e used for updating the reference data of the system. The system was t ested over a period of four months with a population of 15 male and fe male speakers with non-correlated training and test data. Its accuracy proved to be satisfactory (91.39% for verification, 90.19% for closed -set identification, 95.28% for open-set identification), considering that the training utterances per speaker do not exceed 50 sec and the test utterances have a duration of 1.3 sec on the average. The accurac y is substantially increased when increasing the length of the test ut terance (e.g. 93.75% verification accuracy for test utterances having an average duration of 4 sec). Additional advantages of the system are the small memory requirements and the fast response.